© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39921
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ларга
    0.68
     saddhim
    0.68
    getCode
    0.67
     UWGM
    0.66
    notlocked
    0.66
    rta
    0.64
    র
    0.63
    埒
    0.63
    तौर
    0.63
    മുണ്ട
    0.63
    POSITIVE LOGITS
     of
    1.10
     or
    0.89
     and
    0.87
     is
    0.77
     has
    0.71
     in
    0.70
     with
    0.70
    of
    0.69
     will
    0.66
     for
    0.66
    Activations Density 0.027%

    No Known Activations